Instance Segmentation of Human Body Parts Using Deep Learning Yolov8 Model
Abstract
Image segmentation constitutes an essential initial stage in digital image processing, wherein the primary objective is to distinguish and separate meaningful objects from the background to facilitate more accurate analysis and recognition. In the context of human body detection, the precise identification and delineation of specific anatomical regions—such as the head, torso, and arms—is particularly important due to the distinct structural and functional characteristics of each part. Aim of the present study introduces a methodological approach and the development of a web-based segmentation system that leverages the YOLOv8 instance segmentation model to partition human body images into four key regions, enhancing both accuracy and usability in downstream applications. A total of 107 images, each manually annotated, were employed and systematically divided into training, validation, and testing datasets. Upon evaluating the model's performance, the highest mean Average Precision (mAP) achieved was 0.979 after 200 training epochs. Additionally, the model attained a precision of 0.914, a recall of 0.995, and an F1-score of 0.95. These results indicate that the proposed instance segmentation framework delivers robust accuracy and dependable performance in segmenting human body parts.References
S. Secinaro, D. Calandra, A. Secinaro, V. Muthurangu, and P. Biancone, “The Role of Artificial Intelligence in Healthcare: A Structured Literature Review,” BMC Med. Inform. Decis. Mak., vol. 21, no. 1, pp. 1–23, 2021, doi: 10.1186/s12911-021-01488-9.
N. H. Oktaviani, M. N. Widyawati, and Kurnianingsih, “Development of a detection tool in pregnant women and its recommendations in utilizing artificial intelligence,” J. Matern. Child Heal., vol. 09, pp. 410–420, 2024.
L. Rundo, R. Pirrone, S. Vitabile, E. Sala, and O. Gambino, “Recent advances of HCI in decision-making tasks for optimized clinical workflows and precision medicine,” J. Biomed. Inform., vol. 108, pp. 1–13, 2020, doi: 10.1016/j.jbi.2020.103479.
D. S. Bukit et al., “Leveraging Machine Learning Techniques for Stunting Detection and Height Growth Prediction in Children Aged 0-5 Years,” Proc. - ELTICOM 2024 8th Int. Conf. Electr. Telecommun. Comput. Eng. Tech-Driven Innov. Glob. Organ. Resil., pp. 130–134, 2024, doi: 10.1109/ELTICOM64085.2024.10864967.
M. Javaid, A. Haleem, R. P. Singh, and M. Ahmed, “Computer vision to enhance healthcare domain: An overview of features, implementation, and opportunities,” Intell. Pharm., vol. 2, no. 6, pp. 792–803, 2024, doi: 10.1016/j.ipha.2024.05.007.
K. K. D. Ramesh, G. Kiran Kumar, K. Swapna, D. Datta, and S. Suman Rajest, “A review of medical image segmentation algorithms,” EAI Endorsed Trans. Pervasive Heal. Technol., vol. 7, no. 27, pp. 1–9, 2021, doi: 10.4108/eai.12-4-2021.169184.
A. Nadeem, A. Jalal, and K. Kim, “Automatic Human Posture Estimation for Sport Activity Recognition with Robust Body Parts Detection and Entropy Markov Model,” Springer, pp. 21465–21498, 2021.
C. Yin, S. Member, J. Tang, and T. Yuan, “Bridging the Gap Between Semantic Segmentation and Instance Segmentation,” IEEE Trans. Multimed., vol. 24, pp. 4183–4196, 2022, doi: 10.1109/TMM.2021.3114541.
F. X. Viana, G. M. Araujo, M. F. Pinto, J. Colares, and D. B. Haddad, “Aerial image instance segmentation through synthetic data using deep learning,” J. Brazilian Soc. Comput. Intell., vol. 18, no. 1, pp. 35–46, 2020, doi: 10.21528/lnlm-vol18-no1-art3.
H. He, J. Zhang, B. Zhuang, J. Cai, and D. Tao, “End-to-end one-shot human parsing,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 12, pp. 14481–14496, 2023, doi: 10.1109/TPAMI.2023.3301672.
M. L. Ali and Z. Zhang, “The YOLO Framework: A Comprehensive Review of Evolution, Applications, and Benchmarks in Object Detection,” Computers, vol. 13, no. 12, 2024, doi: 10.3390/computers13120336.
M. S, M. Saranya S, K. T, and S. P, “Image detection and segmentation using YOLO v5 for surveillance,” in International Conference on Software Engineering and Machine Learning, 2023, pp. 142–147. doi: 10.54254/2755-2721/8/20230109.
N. P. Motwani and S. S, “Human activities detection using deep learning technique- YOLOv8,” in ITM Web of Conferences, 2023, pp. 1–8. doi: 10.1051/itmconf/20235603003.
F. Jiang et al., “Artificial Intelligence in Healthcare: Past, Present and Future,” 2017. doi: 10.1136/svn-2017-000101.
G. Wang, Y. Chen, P. An, H. Hong, J. Hu, and T. Huang, “UAV-YOLOv8: A small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios,” Sensors, vol. 23, no. 16, pp. 1–27, 2023, doi: 10.3390/s23167190.
Y. Yang, Z. Song, T. D. Palaoag, and S. Li, “An Improved Model for People Detection Based on YOLOv8,” Proceeding 2024 9th Int. Conf. Inf. Technol. Digit. Appl. ICITDA 2024, pp. 1–7, 2024, doi: 10.1109/ICITDA64560.2024.10809805.
A. Dr. Jaka Sunardi, M.Kes., A. dr. Prijo Sudibjo, M.Kes., Sp.S., and M. S. Dr. Endang Rini Sukamti, DIKTAT Anatomi Manusia, 1st ed., vol. 11, no. 1. Yogyakarta: UNY Press, 2020. [Online]. Available: https://books.google.co.id/books?id=8AcREAAAQBAJ
Y. Yu et al., “Techniques and Challenges of Image Segmentation: A Review,” Electron., vol. 12, no. 5, 2023, doi: 10.3390/electronics12051199.
W. Cai, Z. Xiong, X. Sun, P. L. Rosin, L. Jin, and X. Peng, “Panoptic segmentation-based attention for image captioning,” Appl. Sci., vol. 10, no. 1, pp. 1–18, 2020, doi: 10.3390/app10010391.
Y. Chuang, S. Zhang, and X. Zhao, “Deep learning-based panoptic segmentation: Recent advances and perspectives,” IET Image Process., vol. 17, no. 10, pp. 2807–2828, 2023, doi: 10.1049/ipr2.12853.
M. Hussain, “YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature toward Digital Manufacturing and Industrial Defect Detection,” Machines, vol. 11, no. 7, 2023, doi: 10.3390/machines11070677.
T. Q. Vinh and H. Byeon, “Enhancing alzheimer’s disease diagnosis: The efficacy of the YOLO algorithm model,” Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 11, pp. 814–821, 2023, doi: 10.14569/IJACSA.2023.0141182.
DOI:
https://doi.org/10.31449/inf.v49i37.9832Downloads
Published
How to Cite
Issue
Section
License
Authors retain copyright in their work. By submitting to and publishing with Informatica, authors grant the publisher (Slovene Society Informatika) the non-exclusive right to publish, reproduce, and distribute the article and to identify itself as the original publisher.
All articles are published under the Creative Commons Attribution license CC BY 3.0. Under this license, others may share and adapt the work for any purpose, provided appropriate credit is given and changes (if any) are indicated.
Authors may deposit and share the submitted version, accepted manuscript, and published version, provided the original publication in Informatica is properly cited.
